Files
rocm-systems/tests/workloads/invdev/mi100/SQ_IFETCH_LEVEL.csv
T
colramos-amd 62d130b458 Initial commit
2022-11-04 14:49:36 -05:00

46 KiB

1IndexKernelNamegpu-idqueue-idqueue-indexpidtidgrdwgrldsscrvgprsgprfbarsigobjGRBM_COUNTGRBM_GUI_ACTIVESQ_WAVESSQ_IFETCHSQ_IFETCH_LEVELSQ_ACCUM_PREV_HIRESDispatchNsBeginNsEndNsCompleteNs
20__amd_rocclr_fillBuffer.kd000935069935074335544322560083264640x00x7fb1e8e04180504417504417524288629145679154810153623212076606776836515120766070209496161207660702127377512076607021386317
31void benchmark_func<short, 256, 8u, 0u>(short, short*) [clone .kd]00293506993507432768256002424124800x00x7fb1e8e35100274572745751281928659111280812076607036018836120766070363287521207660703633467212076607036343359
42void benchmark_func<float, 256, 8u, 0u>(float, float*) [clone .kd]0049350699350744194304256002424129280x7fb2f49b39000x7fb1e8e35140221451221451655369175041377001762710812076607036410164120766070366343501207660703676987012076607036773860
53void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 0u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0069350699350744194304256003624136320x7fb2f49b38000x7fb1e8e351803985293985296553612451841763632259511612076607036850743120766070370349891207660703728842812076607037361443
64void benchmark_func<double, 256, 8u, 0u>(double, double*) [clone .kd]0089350699350744194304256002824140800x7fb2f49b37000x7fb1e8e351c0410715410715655369830401368331747553212076607037393453120766070375855461207660703784650512076607037914191
75void benchmark_func<__half2, 256, 8u, 0u>(__half2, __half2*) [clone .kd]00109350699350744194304256002424145280x7fb2f49b36000x7fb1e8e352002267052267056553610485761532901953714412076607037942794120766070381389841207660703827850412076607038282236
86void benchmark_func<int, 256, 8u, 0u>(int, int*) [clone .kd]00129350699350744194304256002424149760x7fb2f49b35000x7fb1e8e35240228547228547655369830401479951896232012076607038336266120766070385157831207660703865626212076607038659818
97void benchmark_func<float, 256, 8u, 1u>(float, float*) [clone .kd]00149350699350744194304256002424154240x7fb2f49b34000x7fb1e8e352802161612161616553610485761467521878445212076607038742652120766070389119411207660703904442012076607039048191
108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 1u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00169350699350744194304256002824161280x7fb2f49b33000x7fb1e8e352c04072194072196553615728642457513143913612076607039102291120766070392896991207660703954937812076607039593976
119void benchmark_func<double, 256, 8u, 1u>(double, double*) [clone .kd]00189350699350744194304256002824168320x7fb2f49b3a000x7fb1e8e353004029614029616553611796481669892133068012076607039617790120766070398133771207660704006953612076607040112089
1210void benchmark_func<__half2, 256, 8u, 1u>(__half2, __half2*) [clone .kd]00209350699350744194304256002424175360x7fb2f49b39000x7fb1e8e353402116992116996553611141121618012074452012076607040145602120766070403284151207660704045753512076607040461169
1311void benchmark_func<int, 256, 8u, 1u>(int, int*) [clone .kd]00229350699350744194304256002424182400x7fb2f49b38000x7fb1e8e353802287372287376553611141121572852010732412076607040513937120766070406917741207660704083241312076607040835916
1412void benchmark_func<float, 256, 8u, 2u>(float, float*) [clone .kd]00249350699350744194304256002424189440x7fb2f49b37000x7fb1e8e353c02170832170836553611796481640322096699212076607040903351120766070410839321207660704121673112076607041220842
1513void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 2u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00269350699350744194304256002824199040x7fb2f49b36000x7fb1e8e354004063134063136553618350082521833225953212076607041274622120766070414484101207660704170584912076607041774261
1614void benchmark_func<double, 256, 8u, 2u>(double, double*) [clone .kd]00289350699350744194304256002824206080x7fb2f49b35000x7fb1e8e354404047154047156553613107201799102305413212076607041801262120766070419863281207660704224360712076607042312442
1715void benchmark_func<__half2, 256, 8u, 2u>(__half2, __half2*) [clone .kd]00309350699350744194304256002424213120x7fb2f49b34000x7fb1e8e354802168172168176553612451841740012230621612076607042340044120766070425264861207660704265944512076607042663235
1816void benchmark_func<int, 256, 8u, 2u>(int, int*) [clone .kd]00329350699350744194304256002424220160x7fb2f49b33000x7fb1e8e354c02193472193476553613107201814512316717212076607042717035120766070428864841207660704302008412076607043024036
1917void benchmark_func<float, 256, 8u, 3u>(float, float*) [clone .kd]00349350699350744194304256002424227200x7fb2f49b3a000x7fb1e8e355002165452165456553613107201806172311839212076607043091932120766070432618431207660704339464212076607043398342
2018void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 3u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00369350699350744194304256002824236800x7fb2f49b39000x7fb1e8e355404104114104116553620971522989573816520012076607043453104120766070436295211207660704389160012076607043936203
2119void benchmark_func<double, 256, 8u, 3u>(double, double*) [clone .kd]00389350699350744194304256002824243840x7fb2f49b38000x7fb1e8e355804052654052656553614417921972542518791212076607043960438120766070441568791207660704441575812076607044457943
2220void benchmark_func<__half2, 256, 8u, 3u>(__half2, __half2*) [clone .kd]00409350699350744194304256002424250880x7fb2f49b37000x7fb1e8e355c02119552119556553613762561900932436115212076607044494992120766070446627971207660704479175712076607044795531
2321void benchmark_func<int, 256, 8u, 3u>(int, int*) [clone .kd]00429350699350744194304256002424257920x7fb2f49b36000x7fb1e8e356002244012244016553615073282115132705206012076607044848650120766070450296761207660704516775512076607045172192
2422void benchmark_func<float, 256, 8u, 4u>(float, float*) [clone .kd]00449350699350744194304256002424264960x7fb2f49b35000x7fb1e8e356402132912132916553614417922064082651139612076607045238255120766070454083941207660704553815312076607045541819
2523void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 4u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00469350699350744194304256002824277120x7fb2f49b34000x7fb1e8e356804065214065216553623592963223214124505212076607045594057120766070457696731207660704602983112076607046098796
2624void benchmark_func<double, 256, 8u, 4u>(double, double*) [clone .kd]00489350699350744194304256002824284160x7fb2f49b33000x7fb1e8e356c04023874023876553615728642102212692687612076607046130294120766070463187901207660704657606912076607046643980
2725void benchmark_func<__half2, 256, 8u, 4u>(__half2, __half2*) [clone .kd]00509350699350744194304256002424291200x7fb2f49b3a000x7fb1e8e357002136972136976553615073282171322773359612076607046675619120766070468610281207660704699238712076607046996125
2826void benchmark_func<int, 256, 8u, 4u>(int, int*) [clone .kd]00529350699350744194304256002424300800x7fb2f49b39000x7fb1e8e357402295712295716553617039362330102984257612076607047049554120766070472315861207660704737286612076607047376693
2927void benchmark_func<float, 256, 8u, 5u>(float, float*) [clone .kd]00549350699350744194304256002424307840x7fb2f49b38000x7fb1e8e357802214412214416553615728642156002752096812076607047442275120766070476107851207660704774694412076607047750738
3028void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 5u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00569350699350744194304256002824320000x7fb2f49b37000x7fb1e8e357c03970833970836553626214403596124604104412076607047804589120766070479735031207660704822806212076607048272499
3129void benchmark_func<double, 256, 8u, 5u>(double, double*) [clone .kd]00589350699350744194304256002824329600x7fb2f49b36000x7fb1e8e358004013294013296553617039362307332953712412076607048299870120766070484848611207660704874150012076607048782758
3230void benchmark_func<__half2, 256, 8u, 5u>(__half2, __half2*) [clone .kd]00609350699350744194304256002424339200x7fb2f49b35000x7fb1e8e358402204672204676553616384002298342938046412076607048815619120766070489877391207660704912309912076607049127129
3331void benchmark_func<int, 256, 8u, 5u>(int, int*) [clone .kd]00629350699350744194304256002424348800x7fb2f49b34000x7fb1e8e358802292252292256553619005442664523418150412076607049180618120766070493566981207660704949829712076607049502086
3432void benchmark_func<float, 256, 8u, 6u>(float, float*) [clone .kd]00649350699350744194304256002424358400x7fb2f49b33000x7fb1e8e358c02138272138276553617039362409603080217212076607049568109120766070497406961207660704987189612076607049875561
3533void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 6u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00669350699350744194304256002824373120x7fb2f49b3a000x7fb1e8e359004062654062656553628835843918655014677612076607049928539120766070501182951207660705037957312076607050448426
3634void benchmark_func<double, 256, 8u, 6u>(double, double*) [clone .kd]00689350699350744194304256002824382720x7fb2f49b39000x7fb1e8e359403998593998596553618350082446853128069212076607050474846120766070506592521207660705091525112076607050982089
3735void benchmark_func<__half2, 256, 8u, 6u>(__half2, __half2*) [clone .kd]00709350699350744194304256002424392320x7fb2f49b38000x7fb1e8e359802214172214176553617694722770533543768812076607051013768120766070511998901207660705133620912076607051339925
3836void benchmark_func<int, 256, 8u, 6u>(int, int*) [clone .kd]00729350699350744194304256002424401920x7fb2f49b37000x7fb1e8e359c02223952223956553620971523095913954121612076607051393314120766070515624491207660705169956812076607051703210
3937void benchmark_func<float, 256, 8u, 7u>(float, float*) [clone .kd]00749350699350744194304256002424411520x7fb2f49b36000x7fb1e8e35a002110732110736553618350082536933248420012076607051769283120766070519354071207660705206516612076607052068881
4038void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 7u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00769350699350744194304256002824426240x7fb2f49b35000x7fb1e8e35a404005954005956553631457284196125365784812076607052120667120766070522995651207660705255716412076607052598215
4139void benchmark_func<double, 256, 8u, 7u>(double, double*) [clone .kd]00789350699350744194304256002824435840x7fb2f49b34000x7fb1e8e35a803969533969536553619660802725343481273212076607052631397120766070527992431207660705305412212076607053123302
4240void benchmark_func<__half2, 256, 8u, 7u>(__half2, __half2*) [clone .kd]00809350699350744194304256002424445440x7fb2f49b33000x7fb1e8e35ac02216112216116553619005442785063571787212076607053150412120766070533488411207660705348452112076607053488431
4341void benchmark_func<int, 256, 8u, 7u>(int, int*) [clone .kd]00829350699350744194304256002424457600x7fb2f49b3a000x7fb1e8e35b002279212279216553622937603070763931902812076607053540548120766070537272401207660705386883912076607053872195
4442void benchmark_func<float, 256, 8u, 8u>(float, float*) [clone .kd]00849350699350744194304256002424467200x7fb2f49b39000x7fb1e8e35b402177872177876553619660802677153418584012076607053937567120766070541077181207660705424131712076607054244868
4543void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 8u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00869350699350744194304256002824484480x7fb2f49b38000x7fb1e8e35b804198974198976553634078724828236178460412076607054297807120766070544731561207660705474403512076607054810621
4644void benchmark_func<double, 256, 8u, 8u>(double, double*) [clone .kd]00889350699350744194304256002824494080x7fb2f49b37000x7fb1e8e35bc04026034026036553620971522763003544094812076607054837240120766070550241941207660705528211312076607055349473
4745void benchmark_func<__half2, 256, 8u, 8u>(__half2, __half2*) [clone .kd]00909350699350744194304256002424503680x7fb2f49b36000x7fb1e8e35c002283132283136553620316162773263547408412076607055376002120766070555611521207660705570227112076607055705706
4846void benchmark_func<int, 256, 8u, 8u>(int, int*) [clone .kd]00929350699350744194304256002424515840x7fb2f49b35000x7fb1e8e35c402353312353316553624903683446164411161612076607055758384120766070559251501207660705607155012076607056075353
4947void benchmark_func<float, 256, 8u, 9u>(float, float*) [clone .kd]00949350699350744194304256002424525440x7fb2f49b34000x7fb1e8e35c802155532155536553620971522854043648462812076607056141606120766070563105891207660705644130812076607056444911
5048void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 9u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]00969350699350744194304256002824542720x7fb2f49b33000x7fb1e8e35cc04219874219876553636700164955146331099612076607056499983120766070566768271207660705694898612076607057018127
5149void benchmark_func<double, 256, 8u, 9u>(double, double*) [clone .kd]00989350699350744194304256002824554880x7fb2f49b3a000x7fb1e8e35d003972253972256553622282243000783848854412076607057044556120766070572318651207660705748738412076607057554595
5250void benchmark_func<__half2, 256, 8u, 9u>(__half2, __half2*) [clone .kd]001009350699350744194304256002424567040x7fb2f49b39000x7fb1e8e35d402144592144596553621626883147384015846812076607057578339120766070577606631207660705789202212076607057895589
5351void benchmark_func<int, 256, 8u, 9u>(int, int*) [clone .kd]001029350699350744194304256002424581760x7fb2f49b38000x7fb1e8e35d802322172322176553626869763757034808872012076607057950000120766070581251411207660705826946112076607058273332
5452void benchmark_func<float, 256, 8u, 10u>(float, float*) [clone .kd]001049350699350744194304256002424593920x7fb2f49b37000x7fb1e8e35dc02196192196196553622282243137714014264412076607058340476120766070585075401207660705864289912076607058646576
5553void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 10u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001069350699350744194304256002824613760x7fb2f49b36000x7fb1e8e35e004179294179296553639321605345326848241612076607058700897120766070588720181207660705914193712076607059210385
5654void benchmark_func<double, 256, 8u, 10u>(double, double*) [clone .kd]001089350699350744194304256002824625920x7fb2f49b35000x7fb1e8e35e404003074003076553623592963098173955981212076607059235020120766070594203361207660705967793512076607059745179
5755void benchmark_func<__half2, 256, 8u, 10u>(__half2, __half2*) [clone .kd]001109350699350744194304256002424638080x7fb2f49b34000x7fb1e8e35e802178252178256553622937603196404093617212076607059769354120766070599507341207660706008337312076607060087326
5856void benchmark_func<int, 256, 8u, 10u>(int, int*) [clone .kd]001129350699350744194304256002424652800x7fb2f49b33000x7fb1e8e35ec02304832304836553628835844065315192910012076607060141447120766070603219321207660706046513212076607060468775
5957void benchmark_func<float, 256, 8u, 11u>(float, float*) [clone .kd]001149350699350744194304256002424664960x7fb2f49b3a000x7fb1e8e35f002209132209136553623592963266314169370412076607060535089120766070606985711207660706083489012076607060838583
6058void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 11u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001169350699350744194304256002824684800x7fb2f49b39000x7fb1e8e35f404160514160516553641943046170877884762812076607060890480120766070610632091207660706133200812076607061400869
6159void benchmark_func<double, 256, 8u, 11u>(double, double*) [clone .kd]001189350699350744194304256002824696960x7fb2f49b38000x7fb1e8e35f804001454001456553624903683279724198218812076607061425675120766070616092871207660706186672612076607061933781
6260void benchmark_func<__half2, 256, 8u, 11u>(__half2, __half2*) [clone .kd]001209350699350744194304256002424709120x7fb2f49b37000x7fb1e8e35fc02247312247316553624248323793114855239212076607061957685120766070621467251207660706228496412076607062288951
6361void benchmark_func<int, 256, 8u, 11u>(int, int*) [clone .kd]001229350699350744194304256002424723840x7fb2f49b36000x7fb1e8e360002265612265616553630801924429215686669212076607062341028120766070625131231207660706265440312076607062658108
6462void benchmark_func<float, 256, 8u, 12u>(float, float*) [clone .kd]001249350699350744194304256002424736000x7fb2f49b35000x7fb1e8e360402178512178516553624903683352194293456412076607062724642120766070628896021207660706302384112076607063027876
6563void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 12u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001269350699350744194304256002824758400x7fb2f49b34000x7fb1e8e360804175054175056553644564486037067749840812076607063081515120766070632569601207660706352719912076607063594460
6664void benchmark_func<double, 256, 8u, 12u>(double, double*) [clone .kd]001289350699350744194304256002824770560x7fb2f49b33000x7fb1e8e360c03993313993316553626214403446444414462812076607063618685120766070638068781207660706406351712076607064106312
6765void benchmark_func<__half2, 256, 8u, 12u>(__half2, __half2*) [clone .kd]001309350699350744194304256002424782720x7fb2f49b3a000x7fb1e8e361002124972124976553625559043648754672454812076607064137640120766070643153561207660706444623512076607064450041
6866void benchmark_func<int, 256, 8u, 12u>(int, int*) [clone .kd]001329350699350744194304256002424800000x7fb2f49b39000x7fb1e8e361402307552307556553632768004622485945583612076607064507318120766070646699141207660706481327412076607064817124
6967void benchmark_func<float, 256, 8u, 13u>(float, float*) [clone .kd]001349350699350744194304256002424812160x7fb2f49b38000x7fb1e8e361802116972116976553626214403630624641002012076607064882636120766070650531131207660706518351212076607065187603
7068void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 13u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001369350699350744194304256002824834560x7fb2f49b37000x7fb1e8e361c04159714159716553647185926193637952758412076607065239670120766070654140711207660706568239012076607065730924
7169void benchmark_func<double, 256, 8u, 13u>(double, double*) [clone .kd]001389350699350744194304256002824849280x7fb2f49b36000x7fb1e8e362003994093994096553627525123654714691426012076607065754918120766070659374291207660706619486812076607066246503
7270void benchmark_func<__half2, 256, 8u, 13u>(__half2, __half2*) [clone .kd]001409350699350744194304256002424864000x7fb2f49b35000x7fb1e8e362402153952153956553626869763846274920592412076607066271589120766070664566271207660706658910612076607066592897
7371void benchmark_func<int, 256, 8u, 13u>(int, int*) [clone .kd]001429350699350744194304256002424881280x7fb2f49b34000x7fb1e8e362802416572416576553634734085422796931040412076607066646276120766070668167851207660706696798512076607066971792
7472void benchmark_func<float, 256, 8u, 14u>(float, float*) [clone .kd]001449350699350744194304256002424896000x7fb2f49b33000x7fb1e8e362c02241232241236553627525123977555090200012076607067062130120766070672279841207660706736638312076607067370233
7573void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 14u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]001469350699350744194304256002824920960x7fb2f49b3a000x7fb1e8e363004167214167216553649807366705098573170412076607067423181120766070675988621207660706786846112076607067890330
7674void benchmark_func<double, 256, 8u, 14u>(double, double*) [clone .kd]001489350699350744194304256002824935680x7fb2f49b39000x7fb1e8e363403989793989796553628835843809814870812812076607067940624120766070681105401207660706836733912076607068417040
7775void benchmark_func<__half2, 256, 8u, 14u>(__half2, __half2*) [clone .kd]001509350699350744194304256002424950400x7fb2f49b38000x7fb1e8e363802220092220096553628180484057015183177612076607068441786120766070686262181207660706876365712076607068767502
7876void benchmark_func<int, 256, 8u, 14u>(int, int*) [clone .kd]001529350699350744194304256002424967680x7fb2f49b37000x7fb1e8e363c02502832502836553636700165031376468177212076607068819809120766070689914961207660706914781612076607069151877
7977void benchmark_func<float, 256, 8u, 15u>(float, float*) [clone .kd]001549350699350744194304256002424982400x7fb2f49b36000x7fb1e8e364002179372179376553628835843916515010217212076607069219864120766070693897351207660706952413412076607069528077
8078void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 15u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0015693506993507441943042560028241007360x7fb2f49b35000x7fb1e8e364404129954129956553651773446818828725511612076607069580394120766070697550131207660707002189212076607070071918
8179void benchmark_func<double, 256, 8u, 15u>(double, double*) [clone .kd]0015893506993507441943042560028241022080x7fb2f49b34000x7fb1e8e364804514094514096553630146564033805173201212076607070097476120766070702815711207660707057373012076607070622873
8280void benchmark_func<__half2, 256, 8u, 15u>(__half2, __half2*) [clone .kd]0016093506993507441943042560024241036800x7fb2f49b33000x7fb1e8e364c02179072179076553629491204238735414287612076607070646778120766070708383691207660707097196812076607070975980
8381void benchmark_func<int, 256, 8u, 15u>(int, int*) [clone .kd]0016293506993507441943042560024241056640x7fb2f49b3a000x7fb1e8e365002643372643376553638666245334386788127212076607071032014120766070712086071207660707137484612076607071379180
8482void benchmark_func<float, 256, 8u, 16u>(float, float*) [clone .kd]0016493506993507441943042560024241071360x7fb2f49b39000x7fb1e8e365402132352132356553630146563961795068614012076607071444261120766070716105261207660707174188512076607071745912
8583void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 16u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0016693506993507441943042560028241098880x7fb2f49b38000x7fb1e8e365804146574146576553654394887042129013882412076607071797729120766070719698841207660707223868312076607072288441
8684void benchmark_func<double, 256, 8u, 16u>(double, double*) [clone .kd]0016893506993507441943042560028241113600x7fb2f49b37000x7fb1e8e365c04556994556996553631457284168705347898012076607072312977120766070724994821207660707279372112076607072842212
8785void benchmark_func<__half2, 256, 8u, 16u>(__half2, __half2*) [clone .kd]0017093506993507441943042560024241128320x7fb2f49b36000x7fb1e8e366002193692193696553630801925077636493363612076607072865866120766070730535601207660707318859912076607073192814
8886void benchmark_func<int, 256, 8u, 16u>(int, int*) [clone .kd]0017293506993507441943042560024241148160x7fb2f49b35000x7fb1e8e366402775472775476553640632325536847068006012076607073246313120766070734178781207660707359275712076607073596585
8987void benchmark_func<float, 256, 8u, 17u>(float, float*) [clone .kd]0017493506993507441943042560024241162880x7fb2f49b34000x7fb1e8e366802230012230016553631457284562165839956812076607073663760120766070738284361207660707396651612076607073970330
9088void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 17u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0017693506993507441943042560028241190400x7fb2f49b33000x7fb1e8e366c041393941393965536570163282943010612223212076607074030302120766070742092351207660707447723412076607074526254
9189void benchmark_func<double, 256, 8u, 17u>(double, double*) [clone .kd]0017893506993507441943042560028241207680x7fb2f49b3a000x7fb1e8e367004033854033856553632768004298555487515612076607074550008120766070747340331207660707499451112076607075021405
9290void benchmark_func<__half2, 256, 8u, 17u>(__half2, __half2*) [clone .kd]0018093506993507441943042560024241224960x7fb2f49b39000x7fb1e8e367402256752256756553632112644883496252115612076607075064275120766070752317911207660707537163012076607075375804
9391void benchmark_func<int, 256, 8u, 17u>(int, int*) [clone .kd]0018293506993507441943042560024241247360x7fb2f49b38000x7fb1e8e367802916172916176553642598405867827498514012076607075427470120766070756012291207660707578442812076607075788272
9492void benchmark_func<float, 256, 8u, 18u>(float, float*) [clone .kd]0018493506993507441943042560024241264640x7fb2f49b37000x7fb1e8e367c02257552257556553632768004998626395221612076607075856068120766070760268271207660707616682712076607076170813
9593void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 18u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0018693506993507441943042560020241279360x7fb2f49b36000x7fb1e8e3680041208941208965536773324897765812509750412076607076223321120766070763996261207660707666714512076607076719043
9694void benchmark_func<double, 256, 8u, 18u>(double, double*) [clone .kd]0018893506993507441943042560028241296640x7fb2f49b35000x7fb1e8e368404076514076516553634078724442975659372412076607076745262120766070769325831207660707719546212076607077244190
9795void benchmark_func<__half2, 256, 8u, 18u>(__half2, __half2*) [clone .kd]0019093506993507441943042560024241313920x7fb2f49b34000x7fb1e8e368802269692269696553633423364586485873501212076607077268305120766070774564211207660707759722112076607077601154
9896void benchmark_func<int, 256, 8u, 18u>(int, int*) [clone .kd]0019293506993507441943042560024241336320x7fb2f49b33000x7fb1e8e368c03014753014756553644564486357168114303212076607077658561120766070778220201207660707801385912076607078060408
9997void benchmark_func<float, 256, 8u, 20u>(float, float*) [clone .kd]0019493506993507441943042560024241353600x7fb2f49b3a000x7fb1e8e369002297372297376553635389445319106816760012076607078098489120766070782645781207660707840537712076607078409077
10098void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 20u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0019693506993507441943042560020241368320x7fb2f49b39000x7fb1e8e36940435539435539655368978432112881514450061612076607078466043120766070786304961207660707891433512076607078935496
10199void benchmark_func<double, 256, 8u, 20u>(double, double*) [clone .kd]0019893506993507441943042560028241385600x7fb2f49b38000x7fb1e8e369803946173946176553636700165140216604834812076607078982634120766070791527341207660707940841312076607079457617
102100void benchmark_func<__half2, 256, 8u, 20u>(__half2, __half2*) [clone .kd]0020093506993507441943042560024241402880x7fb2f49b37000x7fb1e8e369c02270752270756553636044805241536717209612076607079483415120766070796658521207660707980665212076607079810473
103101void benchmark_func<int, 256, 8u, 20u>(int, int*) [clone .kd]0020293506993507441943042560024241427840x7fb2f49b36000x7fb1e8e36a003290973290976553648496646926908798046012076607079864043120766070800408911207660708025161012076607080300435
104102void benchmark_func<float, 256, 8u, 22u>(float, float*) [clone .kd]0020493506993507441943042560024241447680x7fb2f49b35000x7fb1e8e36a402264032264036553638010885812537437240812076607080338455120766070805039291207660708064440812076607080648081
105103void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 22u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0020693506993507441943042560020241457280x7fb2f49b34000x7fb1e8e36a804705374705376553614548992182863723403432412076607080700419120766070808781671207660708118552612076607081234983
106104void benchmark_func<double, 256, 8u, 22u>(double, double*) [clone .kd]0020893506993507441943042560028241477120x7fb2f49b33000x7fb1e8e36ac04046514046516553639321605181046621172012076607081261102120766070814436051207660708170568412076607081752906
107105void benchmark_func<__half2, 256, 8u, 22u>(__half2, __half2*) [clone .kd]0021093506993507441943042560024241496960x7fb2f49b3a000x7fb1e8e36b002188332188336553638666246186507926251612076607081776971120766070819588031207660708209528212076607082099411
108106void benchmark_func<int, 256, 8u, 22u>(int, int*) [clone .kd]0021293506993507441943042560024241521920x7fb2f49b39000x7fb1e8e36b403569153569156553652428807193989207529212076607082150867120766070823272811207660708255608012076607082603138
109107void benchmark_func<float, 256, 8u, 24u>(float, float*) [clone .kd]0021493506993507441943042560024241541760x7fb2f49b38000x7fb1e8e36b802229132229136553640632326274268031996012076607082639516120766070828039191207660708294247912076607082946397
110108void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 24u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0021693506993507441943042560020241556480x7fb2f49b37000x7fb1e8e36bc05031395031396553610027008126241116122007612076607082998554120766070831810381207660708351015612076607083559106
111109void benchmark_func<double, 256, 8u, 24u>(double, double*) [clone .kd]0021893506993507441943042560028241576320x7fb2f49b36000x7fb1e8e36c004064814064816553641943045456646973616412076607083581979120766070837674791207660708403147912076607084082600
112110void benchmark_func<__half2, 256, 8u, 24u>(__half2, __half2*) [clone .kd]0022093506993507441943042560024241596160x7fb2f49b35000x7fb1e8e36c402218992218996553641287686227347965254412076607084104861120766070843058771207660708444347612076607084446487
113111void benchmark_func<int, 256, 8u, 24u>(int, int*) [clone .kd]0022293506993507441943042560024241623680x7fb2f49b34000x7fb1e8e36c803810413810416553656360967707759824700012076607084501569120766070846775561207660708492299512076607084969299
114112void benchmark_func<float, 256, 8u, 28u>(float, float*) [clone .kd]0022493506993507441943042560024241646080x7fb2f49b33000x7fb1e8e36cc02266192266196553645875206558998396180812076607085013682120766070851809141207660708532139412076607085324680
115113void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 28u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0022693506993507441943042560020241663360x7fb2f49b3a000x7fb1e8e36d005759855759856553611075584139418917837467212076607085378210120766070855466731207660708592523212076607085971684
116114void benchmark_func<double, 256, 8u, 28u>(double, double*) [clone .kd]0022893506993507441943042560028241685760x7fb2f49b39000x7fb1e8e36d404019634019636553647185926698148582563212076607085995318120766070861860311207660708644635012076607086466625
117115void benchmark_func<__half2, 256, 8u, 28u>(__half2, __half2*) [clone .kd]0023093506993507441943042560024241708160x7fb2f49b38000x7fb1e8e36d802236812236816553646530566679468559490012076607086512831120766070866783501207660708681738912076607086820583
118116void benchmark_func<int, 256, 8u, 28u>(int, int*) [clone .kd]0023293506993507441943042560024241740800x7fb2f49b37000x7fb1e8e36dc043467543467565536642252889448011478793612076607086873562120766070870725881207660708735274712076607087401173
119117void benchmark_func<float, 256, 8u, 32u>(float, float*) [clone .kd]0023493506993507441943042560024241765760x7fb2f49b36000x7fb1e8e36e0022296922296965536511180879111910134258812076607087445996120766070876167471207660708775578612076607087758949
120118void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 32u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0023693506993507441943042560020241777920x7fb2f49b35000x7fb1e8e36e406475236475236553615007744188159724100216812076607087810795120766070879842651207660708841114412076607088458590
121119void benchmark_func<double, 256, 8u, 32u>(double, double*) [clone .kd]0023893506993507441943042560028241802880x7fb2f49b34000x7fb1e8e36e804090814090816553652428806873138831652412076607088483737120766070886764231207660708894186312076607088988656
122120void benchmark_func<__half2, 256, 8u, 32u>(__half2, __half2*) [clone .kd]0024093506993507441943042560024241827840x7fb2f49b33000x7fb1e8e36ec021975521975565536517734478995910105138012076607089016728120766070892113021207660708934778112076607089351190
123121void benchmark_func<int, 256, 8u, 32u>(int, int*) [clone .kd]0024293506993507441943042560024241863040x7fb2f49b3a000x7fb1e8e36f0048840148840165536720896097903612638174412076607089404860120766070895759411207660708989162012076607089939795
124122void benchmark_func<float, 256, 8u, 40u>(float, float*) [clone .kd]0024493506993507441943042560024241893120x7fb2f49b39000x7fb1e8e36f4024483524483565536616038494485112097217212076607089986332120766070901610591207660709031465812076607090317918
125123void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 40u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0024693506993507441943042560020241907840x7fb2f49b38000x7fb1e8e36f807849297849296553617104896214846627514045212076607090370406120766070905549781207660709107321612076607091095254
126124void benchmark_func<double, 256, 8u, 40u>(double, double*) [clone .kd]0024893506993507441943042560028241937920x7fb2f49b37000x7fb1e8e36fc045689945689965536629145683556810719053612076607091150217120766070913192951207660709161753412076607091664734
127125void benchmark_func<__half2, 256, 8u, 40u>(__half2, __half2*) [clone .kd]0025093506993507441943042560024241968000x7fb2f49b36000x7fb1e8e3700024572924572965536622592091579511732686412076607091693597120766070918775341207660709203225312076607092035654
128126void benchmark_func<int, 256, 8u, 40u>(int, int*) [clone .kd]0025293506993507441943042560024242010880x7fb2f49b35000x7fb1e8e37040593875593875655368781824124956516013343212076607092090175120766070922760921207660709266217112076607092708766
129127void benchmark_func<float, 256, 8u, 48u>(float, float*) [clone .kd]0025493506993507441943042560024242046080x7fb2f49b34000x7fb1e8e37080276121276121655367208960100843512892710412076607092748720120766070929141701207660709308953012076607093092900
130128void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 48u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0025693506993507441943042560020242060800x7fb2f49b33000x7fb1e8e370c09425399425396553619202048241429430816010412076607093146069120766070933239291207660709394664712076607093994998
131129void benchmark_func<double, 256, 8u, 48u>(double, double*) [clone .kd]0025893506993507441943042560028242096000x7fb2f49b3a000x7fb1e8e3710050519350519365536734003295985112295107212076607094019965120766070942120861207660709454296512076607094590246
132130void benchmark_func<__half2, 256, 8u, 48u>(__half2, __half2*) [clone .kd]0026093506993507441943042560024242131200x7fb2f49b39000x7fb1e8e37140280955280955655367274496103597413270340412076607094614210120766070947962451207660709497432412076607094977506
133131void benchmark_func<int, 256, 8u, 48u>(int, int*) [clone .kd]0026293506993507441943042560024242181760x7fb2f49b38000x7fb1e8e371807002257002256553610354688145151318597458812076607095031627120766070952111231207660709566856212076607095716130
134132void benchmark_func<float, 256, 8u, 56u>(float, float*) [clone .kd]0026493506993507441943042560024242222080x7fb2f49b37000x7fb1e8e371c0370371370371655368257536115186114739180412076607095756805120766070959237611207660709616136012076607096209638
135133void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 56u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0026693506993507441943042560020242239360x7fb2f49b36000x7fb1e8e37200106562510656256553621299200266981134166280412076607096234704120766070964202401207660709712407712076607097171597
136134void benchmark_func<double, 256, 8u, 56u>(double, double*) [clone .kd]0026893506993507441943042560028242279680x7fb2f49b35000x7fb1e8e37240567019567019655368388608119213415281150012076607097204899120766070973927171207660709776583512076607097812710
137135void benchmark_func<__half2, 256, 8u, 56u>(__half2, __half2*) [clone .kd]0027093506993507441943042560024242320000x7fb2f49b34000x7fb1e8e37280374217374217655368323072128930116497482812076607097836945120766070980346351207660709827511412076607098329020
138136void benchmark_func<int, 256, 8u, 56u>(int, int*) [clone .kd]0027293506993507441943042560024242378240x7fb2f49b33000x7fb1e8e372c08066998066996553611927552161080620624870812076607098355369120766070985555931207660709908391112076607099132585
139137void benchmark_func<float, 256, 8u, 64u>(float, float*) [clone .kd]0027493506993507441943042560024242423680x7fb2f49b3a000x7fb1e8e37300349865349865655369306112144543818510051612076607099174683120766070993435911207660709956871012076607099616745
140138void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 64u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0027693506993507441943042560020242435840x7fb2f49b39000x7fb1e8e37340120896312089636553629163520365237846759806812076607099646741120766070998235891207660710062502712076607100675295
141139void benchmark_func<double, 256, 8u, 64u>(double, double*) [clone .kd]0027893506993507441943042560028242481280x7fb2f49b38000x7fb1e8e37380642609642609655369437184125938716122034012076607100700642120766071008859861207660710130806512076607101377501
142140void benchmark_func<__half2, 256, 8u, 64u>(__half2, __half2*) [clone .kd]0028093506993507441943042560024242526720x7fb2f49b37000x7fb1e8e373c0352675352675655369371648136240117443770012076607101401405120766071015869441207660710181286312076607101853486
143141void benchmark_func<int, 256, 8u, 64u>(int, int*) [clone .kd]0028293506993507441943042560024242592640x7fb2f49b36000x7fb1e8e374009092979092976553613500416193939224947021212076607101889804120766071020709421207660710266854012076607102736529
144142void benchmark_func<float, 256, 8u, 80u>(float, float*) [clone .kd]0028493506993507441943042560024242648320x7fb2f49b35000x7fb1e8e374404196434196436553611403264181072723178060012076607102773227120766071029510991207660710322149912076607103288866
145143void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 80u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0028693506993507441943042560020242663040x7fb2f49b34000x7fb1e8e37480148691314869136553633357824417684753446284012076607103313472120766071034986181207660710448453512076607104551705
146144void benchmark_func<double, 256, 8u, 80u>(double, double*) [clone .kd]0028893506993507441943042560028242718720x7fb2f49b33000x7fb1e8e374c07767797767796553611534336155971519923744012076607104575750120766071047696541207660710528469212076607105351593
147145void benchmark_func<__half2, 256, 8u, 80u>(__half2, __half2*) [clone .kd]0029093506993507441943042560024242774400x7fb2f49b3a000x7fb1e8e375004267534267536553611534336185140323692794812076607105381649120766071055666111207660710584069112076607105906605
148146void benchmark_func<int, 256, 8u, 80u>(int, int*) [clone .kd]0029293506993507441943042560012242799360x7fb2f49b39000x7fb1e8e37540112539511253956553619267584243027631102880012076607105932844120766071061262901207660710686500712076607106933055
149147void benchmark_func<float, 256, 8u, 96u>(float, float*) [clone .kd]0029493506993507441943042560024242865280x7fb2f49b38000x7fb1e8e375804861134861136553613500416198964325474848012076607106973300120766071071454871207660710746148612076607107527841
150148void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 96u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0029693506993507441943042560020242880000x7fb2f49b37000x7fb1e8e375c0176834717683476553637552128469810060165601612076607107554941120766071077421251207660710891492112076607108982587
151149void benchmark_func<double, 256, 8u, 96u>(double, double*) [clone .kd]0029893506993507441943042560032242945920x7fb2f49b36000x7fb1e8e376009161459161456553613631488183759423500921612076607109018424120766071092042001207660710981411812076607109881229
152150void benchmark_func<__half2, 256, 8u, 96u>(__half2, __half2*) [clone .kd]0030093506993507441943042560024243011840x7fb2f49b35000x7fb1e8e376404928114928116553613631488207801426604883612076607109909411120766071101105971207660711043027612076607110499398
153151void benchmark_func<int, 256, 8u, 96u>(int, int*) [clone .kd]0030293506993507441943042560012243049600x7fb2f49b34000x7fb1e8e37680133606513360656553621692416274060235026984012076607110534754120766071107045161207660711158275312076607111651411
154152void benchmark_func<float, 256, 8u, 128u>(float, float*) [clone .kd]0030493506993507441943042560024243136000x7fb2f49b33000x7fb1e8e376c06327476327476553617694720278885035680926812076607111700342120766071118673921207660711228099112076607112347516
155153void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 128u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0030693506993507441943042560020243148160x7fb2f49b3a000x7fb1e8e37700233239323323936553657475072719367492084710812076607112378243120766071125640301207660711411298512076607114179414
156154void benchmark_func<double, 256, 8u, 128u>(double, double*) [clone .kd]0030893506993507441943042560020243175680x7fb2f49b39000x7fb1e8e37740120032312003236553619660800247136531621724412076607114210191120766071143957041207660711519090212076607115257670
157155void benchmark_func<__half2, 256, 8u, 128u>(__half2, __half2*) [clone .kd]0031093506993507441943042560012243203200x7fb2f49b38000x7fb1e8e377806401696401696553620381696257427032948226012076607115287555120766071154733011207660711588866012076607115954926
158156void benchmark_func<int, 256, 8u, 128u>(int, int*) [clone .kd]0031293506993507441943042560012243240960x7fb2f49b37000x7fb1e8e377c0175702717570276553628704768361373446249234012076607115982508120766071161708991207660711732961512076607117396298
159157void benchmark_func<float, 256, 8u, 256u>(float, float*) [clone .kd]0031493506993507441943042560012243288960x7fb2f49b36000x7fb1e8e37800120082512008256553636634624462705259239312412076607117434739120766071176040141207660711839089212076607118457622
160158void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 256u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0031693506993507441943042560020243301120x7fb2f49b35000x7fb1e8e37840458381145838116553610584064013238877169493608012076607118490763120766071186809711207660712173296212076607121800290
161159void benchmark_func<double, 256, 8u, 256u>(double, double*) [clone .kd]0031893506993507441943042560020243328640x7fb2f49b34000x7fb1e8e37880232434523243456553638535168483330661803932812076607121831808120766071220276811207660712357055612076607123639781
162160void benchmark_func<__half2, 256, 8u, 256u>(__half2, __half2*) [clone .kd]0032093506993507441943042560012243356160x7fb2f49b33000x7fb1e8e378c0120262712026276553639124992490965562851776412076607123663065120766071238579151207660712464735312076607124713499
163161void benchmark_func<int, 256, 8u, 256u>(int, int*) [clone .kd]0032293506993507441943042560012243393920x7fb2f49b3a000x7fb1e8e37900344292934429296553655771136701093589748835212076607124738455120766071249297521207660712721246512076607127280584
164162void benchmark_func<float, 256, 8u, 512u>(float, float*) [clone .kd]0032493506993507441943042560012243441920x7fb2f49b39000x7fb1e8e379402322507232250765536725483529109453116616162012076607127325978120766071274977441207660712903325912076607129100299
165163void benchmark_func<HIP_vector_type<float, 2u>, 256, 8u, 512u>(HIP_vector_type<float, 2u>, HIP_vector_type<float, 2u>*) [clone .kd]0032693506993507441943042560020243454080x7fb2f49b38000x7fb1e8e37980908625790862576553621069824026342168337258154412076607129130234120766071293146981207660713537260012076607135440141
166164void benchmark_func<double, 256, 8u, 512u>(double, double*) [clone .kd]0032893506993507441943042560020243481600x7fb2f49b37000x7fb1e8e379c04572891457289165536762839049533686122183566412076607135472702120766071356497191207660713869307012076607138760458
167165void benchmark_func<__half2, 256, 8u, 512u>(__half2, __half2*) [clone .kd]0033093506993507441943042560012243509120x7fb2f49b36000x7fb1e8e37a002328209232820965536773980169689987124075085612076607138789231120766071389857091207660714052490412076607140593778
168166void benchmark_func<int, 256, 8u, 512u>(int, int*) [clone .kd]00332935069935074419430425600122400x7fb2f49b35000x7fb1e8e37a40681172368117236553611082137613888539177797916412076607140622982120766071408119431207660714534008912076607145411670